skip to main content


Title: Fine-grained address segmentation for attention-based variable-degree prefetching
Machine learning algorithms have shown potential to improve prefetching performance by accurately predicting future memory accesses. Existing approaches are based on the modeling of text prediction, considering prefetching as a classification problem for sequence prediction. However, the vast and sparse memory address space leads to large vocabulary, which makes this modeling impractical. The number and order of outputs for multiple cache line prefetching are also fundamentally different from text prediction. We propose TransFetch, a novel way to model prefetching. To reduce vocabulary size, we use fine-grained address segmentation as input. To predict unordered sets of future addresses, we use delta bitmaps for multiple outputs. We apply an attention-based network to learn the mapping between input and output. Prediction experiments demonstrate that address segmentation achieves 26% - 36% higher F1-score than delta inputs and 15% - 24% higher F1-score than page & offset inputs for SPEC 2006, SPEC 2017, and GAP benchmarks. Simulation results show that TransFetch achieves 38.75% IPC improvement compared with no prefetching, outperforming the best-performing rule-based prefetcher BOP by 10.44% and ML-based prefetcher Voyager by 6.64%.  more » « less
Award ID(s):
1912680
NSF-PAR ID:
10376312
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Proceedings of the 19th ACM International Conference on Computing Frontiers
Page Range / eLocation ID:
103 to 112
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. This paper presents Voyager, a novel neural network for data prefetching. Unlike previous neural models for prefetching, which are limited to learning delta correlations, our model can also learn address correlations, which are important for prefetching irregular sequences of memory accesses. The key to our solution is its hierarchical structure that separates addresses into pages and offsets and that introduces a mechanism for learning important relations among pages and offsets. Voyager provides significant prediction benefits over current data prefetchers. For a set of irregular programs from the SPEC 2006 and GAP benchmark suites, Voyager sees an average IPC improvement of 41.6% over a system with no prefetcher, compared with 21.7% and 28.2%, respectively, for idealized Domino and ISB prefetchers. We also find that for two commercial workloads for which current data prefetchers see very little benefit, Voyager dramatically improves both accuracy and coverage. At present, slow training and prediction preclude neural models from being practically used in hardware, but Voyager’s overheads are significantly lower—in every dimension—than those of previous neural models. For example, computation cost is reduced by 15- 20×, and storage overhead is reduced by 110-200×. Thus, Voyager represents a significant step towards a practical neural prefetcher. 
    more » « less
  2. null (Ed.)
    The number of published manufacturing science digital articles available from scientifc journals and the broader web have exponentially increased every year since the 1990s. To assimilate all of this knowledge by a novice engineer or an experienced researcher, requires signifcant synthesis of the existing knowledge space contained within published material, to fnd answers to basic and complex queries. Algorithmic approaches through machine learning and specifcally Natural Language Processing (NLP) on a domain specifc area such as manufacturing, is lacking. One of the signifcant challenges to analyzing manufacturing vocabulary is the lack of a named entity recognition model that enables algorithms to classify the manufacturing corpus of words under various manufacturing semantic categories. This work presents a supervised machine learning approach to categorize unstructured text from 500K+manufacturing science related scientifc abstracts and labelling them under various manufacturing topic categories. A neural network model using a bidirectional long-short term memory, plus a conditional random feld (BiLSTM+CRF) is trained to extract information from manufacturing science abstracts. Our classifer achieves an overall accuracy (f1-score) of 88%, which is quite near to the state-of-the-art performance. Two use case examples are presented that demonstrate the value of the developed NER model as a Technical Language Processing (TLP) workfow on manufacturing science documents. The long term goal is to extract valuable knowledge regarding the connections and relationships between key manufacturing concepts/entities available within millions of manufacturing documents into a structured labeled-property graph data structure that allow for programmatic query and retrieval. 
    more » « less
  3. The past decade has seen the rise of highly successful cache replacement policies that are based on binary prediction. For example, the Hawkeye policy learns whether lines loaded by a given PC are Cache Friendly (likely to remain in the cache if Belady’s MIN policy had been used) or Cache Averse (likely to be evicted by Belady’s MIN policy). In this paper, we instead present a cache replacement policy that is based on multiclass prediction, which allows it to directly mimic Belady’s MIN policy in a surprisingly simple and effective way. Our policy uses a PC-based predictor to learn each cache line’s reuse distance; it then evicts lines based on their predicted time of reuse. We show that our use of multiclass prediction is more effective than binary prediction because it allows for a finer-grained ordering of cache lines during eviction and because it is more robust to prediction errors.Our empirical results show that our new policy, which we refer to as Mockingjay, outperforms the previous state-of-the-art on both single-core and multi-core platforms and both with and without a prefetcher. For example, with no prefetcher, on a mix of 100 multi-core workloads from the SPEC 2006, SPEC 2017, and GAP benchmark suites, Mockingjay sees an average improvement over LRU of 15.2%, compared to 7.6% for SHiP and 12.9% for Hawkeye. On a single-core platform, Mockingjay’s improvement over LRU is 5.7%, which approaches the 6.0% improvement of Belady MIN’s unrealizable policy. On a single-core platform (with a prefetcher) running the high-MPKI CVP workloads, Mockingjay’s improvement over LRU is 20.1%, compared to 13.4% for Hawkeye. 
    more » « less
  4. Abstract

    Many studies of Earth surface processes and landscape evolution rely on having accurate and extensive data sets of surficial geologic units and landforms. Automated extraction of geomorphic features using deep learning provides an objective way to consistently map landforms over large spatial extents. However, there is no consensus on the optimal input feature space for such analyses. We explore the impact of input feature space for extracting geomorphic features from land surface parameters (LSPs) derived from digital terrain models (DTMs) using convolutional neural network (CNN)‐based semantic segmentation deep learning. We compare four input feature space configurations: (a) a three‐layer composite consisting of a topographic position index (TPI) calculated using a 50 m radius circular window, square root of topographic slope, and TPI calculated using an annulus with a 2 m inner radius and 10 m outer radius, (b) a single illuminating position hillshade, (c) a multidirectional hillshade, and (d) a slopeshade. We test each feature space input using three deep learning algorithms and four use cases: two with natural features and two with anthropogenic features. The three‐layer composite generally provided lower overall losses for the training samples, a higher F1‐score for the withheld validation data, and better performance for generalizing to withheld testing data from a new geographic extent. Results suggest that CNN‐based deep learning for mapping geomorphic features or landforms from LSPs is sensitive to input feature space. Given the large number of LSPs that can be derived from DTM data and the variety of geomorphic mapping tasks that can be undertaken using CNN‐based methods, we argue that additional research focused on feature space considerations is needed and suggest future research directions. We also suggest that the three‐layer composite implemented here can offer better performance in comparison to using hillshades or other common terrain visualization surfaces and is, thus, worth considering for different mapping and feature extraction tasks.

     
    more » « less
  5. null (Ed.)
    The prevalence of mobile phones and wearable devices enables the passive capturing and modeling of human behavior at an unprecedented resolution and scale. Past research has demonstrated the capability of mobile sensing to model aspects of physical health, mental health, education, and work performance, etc. However, most of the algorithms and models proposed in previous work follow a one-size-fits-all (i.e., population modeling) approach that looks for common behaviors amongst all users, disregarding the fact that individuals can behave very differently, resulting in reduced model performance. Further, black-box models are often used that do not allow for interpretability and human behavior understanding. We present a new method to address the problems of personalized behavior classification and interpretability, and apply it to depression detection among college students. Inspired by the idea of collaborative-filtering, our method is a type of memory-based learning algorithm. It leverages the relevance of mobile-sensed behavior features among individuals to calculate personalized relevance weights, which are used to impute missing data and select features according to a specific modeling goal (e.g., whether the student has depressive symptoms) in different time epochs, i.e., times of the day and days of the week. It then compiles features from epochs using majority voting to obtain the final prediction. We apply our algorithm on a depression detection dataset collected from first-year college students with low data-missing rates and show that our method outperforms the state-of-the-art machine learning model by 5.1% in accuracy and 5.5% in F1 score. We further verify the pipeline-level generalizability of our approach by achieving similar results on a second dataset, with an average improvement of 3.4% across performance metrics. Beyond achieving better classification performance, our novel approach is further able to generate personalized interpretations of the models for each individual. These interpretations are supported by existing depression-related literature and can potentially inspire automated and personalized depression intervention design in the future 
    more » « less